Experimental: Handle degraded deletions by comparing object versions with epochs

CAUTION! This version is not fool proof yet. If you purge data of an OSD by
overwriting the disk with zeroes and restart it then the same data will also
be removed from other replicas :-).

I plan to add protection from this situation before merging it into master.
The idea is to make each OSD store a random "cookie" on disk and remove itself
from history automatically if the cookie doesn't match.
This commit is contained in:
Vitaliy Filippov
2023-04-29 00:21:22 +03:00
parent 5e295e346e
commit 4c9bf6727b
20 changed files with 553 additions and 105 deletions
+11 -4
View File
@@ -10,18 +10,25 @@ function add_pg_history(new_pg_history, new_pg, prev_pgs, prev_pg_history, old_p
if (!new_pg_history[new_pg])
{
new_pg_history[new_pg] = {
osd_sets: {},
osd_set_epochs: {},
all_peers: {},
epoch: 0,
};
}
const nh = new_pg_history[new_pg], oh = prev_pg_history[old_pg];
nh.osd_sets[prev_pgs[old_pg].join(' ')] = prev_pgs[old_pg];
nh.osd_set_epochs[prev_pgs[old_pg].join(' ')] = { osd_set: prev_pgs[old_pg] };
if (oh && oh.osd_sets && oh.osd_sets.length)
{
for (const pg of oh.osd_sets)
{
nh.osd_sets[pg.join(' ')] = pg.map(osd_num => Number(osd_num));
nh.osd_set_epochs[pg.join(' ')] = { osd_set: pg.map(osd_num => Number(osd_num)) };
}
}
if (oh && oh.osd_set_epochs && oh.osd_set_epochs.length)
{
for (const pg of oh.osd_set_epochs)
{
nh.osd_set_epochs[pg.osd_set.join(' ')] = { osd_set: pg.osd_set.map(osd_num => Number(osd_num)) };
}
}
if (oh && oh.all_peers && oh.all_peers.length)
@@ -39,7 +46,7 @@ function add_pg_history(new_pg_history, new_pg, prev_pgs, prev_pg_history, old_p
function finish_pg_history(merged_history)
{
merged_history.osd_sets = Object.values(merged_history.osd_sets);
merged_history.osd_set_epochs = Object.values(merged_history.osd_set_epochs);
merged_history.all_peers = Object.values(merged_history.all_peers);
}
+6 -13
View File
@@ -286,7 +286,12 @@ const etcd_tree = {
history: {
/* <pool_id>: {
<pg_id>: {
osd_sets: osd_num_t[][],
osd_set_epochs: {
osd_set: osd_num_t[],
min_epoch: uint64_t,
max_epoch: uint64_t,
}[],
osd_sets: osd_num_t[][], // outdated
all_peers: osd_num_t[],
epoch: uint64_t,
},
@@ -968,18 +973,6 @@ class Mon
osd_set,
primary: this.pick_primary(pool_id, osd_set, up_osds, aff_osds),
};
if (prev_pgs[i] && prev_pgs[i].join(' ') != osd_set.join(' ') &&
prev_pgs[i].filter(osd_num => osd_num).length > 0)
{
pg_history[i] = pg_history[i] || {};
pg_history[i].osd_sets = pg_history[i].osd_sets || [];
pg_history[i].osd_sets.push(prev_pgs[i]);
}
if (pg_history[i] && pg_history[i].osd_sets)
{
pg_history[i].osd_sets = Object.values(pg_history[i].osd_sets
.reduce((a, c) => { a[c.join(' ')] = c; return a; }, {}));
}
});
for (let i = 0; i < new_pgs.length || i < prev_pgs.length; i++)
{